← Back to Skills Marketplace
PDF Translate
by
ChrisLee121
· GitHub ↗
· v4.0.0
556
Downloads
0
Stars
5
Active Installs
1
Versions
Install in OpenClaw
/install pdf-translate
Description
Translates PDF documents to Chinese with professional typography. Extracts text, translates section-by-section into well-structured Markdown, then generates...
Usage Guidance
This skill appears coherent and implements what it claims: it extracts text from PDFs, expects the agent (model) to do the translation, then converts the resulting Markdown to a styled PDF using the provided scripts. Before installing/use: 1) be prepared to install system dependencies (weasyprint requires libpango/libgobject; instructions include brew/apt notes). 2) Understand that the translation step is performed by your agent/model — sending extracted text to the model may expose document contents to your model provider; do not use it on highly sensitive documents unless you are comfortable with that. 3) The scripts read the PDF you supply and write .md/.pdf alongside it (ensure you trust the skill and the environment where files are placed). 4) No network endpoints, secrets, or unrelated credentials are requested by the skill, but you should still review any runtime logs if used in a multi-tenant environment. If you want stricter guarantees, run the scripts locally with an on-premise model or perform translation offline.
Capability Analysis
Type: OpenClaw Skill
Name: pdf-translate
Version: 4.0.0
The skill is classified as suspicious due to a significant Remote Code Execution (RCE) vulnerability. The `SKILL.md` file instructs the AI agent to execute shell commands (e.g., `python3 ${SKILL_DIR}/scripts/md2pdf.py "输入.md" "输出.pdf"`). The Python scripts (`scripts/md2pdf.py`, `scripts/translate_pdf.py`) take input and output filenames directly from command-line arguments (`sys.argv`) without explicit sanitization for shell metacharacters. If the OpenClaw agent does not adequately sanitize user-provided filenames before passing them to these shell commands, an attacker could inject arbitrary commands, leading to RCE. Additionally, `scripts/generate_complete_pdf.py` contains a hardcoded absolute output path, which is a minor vulnerability for unintended file overwrites.
Capability Assessment
Purpose & Capability
Name/description (PDF → Chinese Markdown + PDF) match the shipped files and runtime instructions. Included scripts (pdf text extraction, Markdown→PDF, legacy reportlab scripts) are entirely consistent with PDF translation and typesetting; README and SKILL.md explicitly describe using the model (Claude) for translation, which aligns with the skill's purpose.
Instruction Scope
SKILL.md instructs the agent to extract text, translate section-by-section, write a .md file and convert to PDF using provided scripts. The instructions reference only local files (input PDF, output .md/.pdf, ${SKILL_DIR}) and required dependencies; they do not instruct reading unrelated system files or env vars, nor do they direct data to external endpoints beyond the expected model usage for translation.
Install Mechanism
No automated install spec is declared (instruction-only installation), which lowers risk. The docs require pip packages (pdfplumber, markdown, weasyprint) and system libs (pango/libgobject) — these are reasonable for the task but do require users to install system libraries (brew/apt) and large Python packages. Nothing is downloaded from obscure URLs and no archives are extracted by the skill itself.
Credentials
The skill declares no required environment variables, no credentials, and no config paths. Scripts only probe common system font paths and read the user-provided PDF; that access is proportional to producing properly typeset PDFs. There are no requests for unrelated secrets or cloud credentials.
Persistence & Privilege
Skill flags are default (not always:true). It does not attempt to modify other skills or system-wide agent settings. It is instruction-only with local scripts and will only run when invoked (agent-autonomy is permitted by platform defaults but not elevated here).
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install pdf-translate - After installation, invoke the skill by name or use
/pdf-translate - Provide required inputs per the skill's parameter spec and get structured output
Version History
v4.0.0
Initial release of PDF translation tool with professional Markdown-to-PDF workflow.
- Provides section-by-section translation of PDFs to Chinese, preserving document structure in Markdown.
- Generates high-quality PDFs from Markdown using weasyprint with full CJK (Chinese, Japanese, Korean) font support and modern typography.
- Fixes previous issues with code blocks displaying Chinese characters incorrectly.
- Includes robust handling of tables, lists, code, blockquotes, and headings.
- Adds `scripts/md2pdf.py` for universal Markdown-to-PDF conversion.
- Reference guides cover translation standards, font configuration, troubleshooting, and complete workflow examples.
Metadata
Frequently Asked Questions
What is PDF Translate?
Translates PDF documents to Chinese with professional typography. Extracts text, translates section-by-section into well-structured Markdown, then generates... It is an AI Agent Skill for Claude Code / OpenClaw, with 556 downloads so far.
How do I install PDF Translate?
Run "/install pdf-translate" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is PDF Translate free?
Yes, PDF Translate is completely free (open-source). You can download, install and use it at no cost.
Which platforms does PDF Translate support?
PDF Translate is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created PDF Translate?
It is built and maintained by ChrisLee121 (@chrislee121); the current version is v4.0.0.
More Skills